A hierarchical approach to large-scale speaker recognition

This paper presents a hierarchical approach to the Large-Scale Speaker Recognition problem. In here the authors present a binary tree data-base approach for arranging the trained speaker models based on a distance measure designed for comparing two sets of distributions. The combination of this hierarchical structure and the distance measure [1] provide the means for conducting a large-scale veri cation task. In addition, two techniques are presented for creating a model of the complement-space to the cohort which is used for rejection purposes. Results are presented for the drastic improvements achieved mainly in reducing the false-acceptance of the speaker veri cation system without any signi cant false-rejection degradation.